TOKENFORGE

shmuelbiller1/TOKENFORGE (JavaScript)

A new way for AI to search for data

View on GitHub

1GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 7f2049abcd (2026-10-14).

Selected work

shmuel biller
@shmuelbiller1

“Add evidence-first offline R&D revision history”. 4 files, 773 lines in backend, desktop.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

Example questions

Where does TOKENFORGE handle “Add evidence-first offline R&D revision history”?
What does backend do in TOKENFORGE?

The prompt

Paste it into your AI agent. It clones shmuelbiller1/TOKENFORGE at the pinned commit and indexes it on your machine.

Search the GitHub repository shmuelbiller1/TOKENFORGE with XERJ (https://hub.xerj.org/corpus/shmuelbiller1--tokenforge).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/shmuelbiller1/TOKENFORGE TOKENFORGE && git -C TOKENFORGE checkout 7f2049abcdb91026365e643c2a3e18d8bd3c9dc7
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./TOKENFORGE --url http://127.0.0.1:9200 --prefix tokenforge --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

shmuel biller API design and specification corpora

Selected work and consent: the XERJ registry.